cwaud commited on
Commit
6c87d3c
·
verified ·
1 Parent(s): a913a9d

Training in progress, step 10, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e554a6ddcf6b401a428ac4c2addea12a796d20914a40c75bdc629d1c1de5c4d
3
  size 41581360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e792701c7d9ab6e457f60fd2ffc8968961757d640b46798fb833bb42b34b1b03
3
  size 41581360
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a2389b005625d3141aebbfb4e36ab87b7472a587fa7e653fed3fbac8862feb8
3
  size 21505540
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27841e17b19ee075263c1ca9a5eb33d5f1da83e54b3a75acadf1cb85537470b2
3
  size 21505540
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7fa4cc5e4c54240a40a09fd5dcfbbb810da4a034b6346087aa3ef80ea319364
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd7fd5d4eafbcf5da125e756357495d09aa3001daed88ea87e0accf560a3325b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.00616121855211364,
5
  "eval_steps": 3,
6
- "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -102,6 +102,13 @@
102
  "eval_samples_per_second": 15.421,
103
  "eval_steps_per_second": 7.723,
104
  "step": 9
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 1,
@@ -116,12 +123,12 @@
116
  "should_evaluate": false,
117
  "should_log": false,
118
  "should_save": true,
119
- "should_training_stop": false
120
  },
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 637624096653312.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.006845798391237378,
5
  "eval_steps": 3,
6
+ "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
102
  "eval_samples_per_second": 15.421,
103
  "eval_steps_per_second": 7.723,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.006845798391237378,
108
+ "grad_norm": 1.0929796695709229,
109
+ "learning_rate": 0.0002,
110
+ "loss": 0.8218,
111
+ "step": 10
112
  }
113
  ],
114
  "logging_steps": 1,
 
123
  "should_evaluate": false,
124
  "should_log": false,
125
  "should_save": true,
126
+ "should_training_stop": true
127
  },
128
  "attributes": {}
129
  }
130
  },
131
+ "total_flos": 687633829724160.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null